Metraipolis › archive › dc_9f8a25edfeeb

IJev: Order-Invariant Decisions via Iterated Cyclic Reordering — arXiv:2611.01015

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01015
License (as archived)
CC0-1.0
Archived
2026-11-03T18:12:17.627Z
SHA-256 of the archived text
97126e90976158b7085720c6288e52840df603330d8ce8c7a46858d022c00c64
Stable URL of this page
https://metraipolis.com/documento/dc_9f8a25edfeeb

How to cite

IJev: Order-Invariant Decisions via Iterated Cyclic Reordering — arXiv:2611.01015 — arXiv (en), https://arxiv.org/abs/2611.01015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9f8a25edfeeb (Metraipolis archive dc_9f8a25edfeeb, sha256 97126e90976158b7085720c6288e52840df603330d8ce8c7a46858d022c00c64)
BibTeX
@misc{dc9f8a25edfeeb,
  title = {IJev: Order-Invariant Decisions via Iterated Cyclic Reordering — arXiv:2611.01015},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01015},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9f8a25edfeeb; sha256 97126e90976158b7085720c6288e52840df603330d8ce8c7a46858d022c00c64},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

System One decision models answer a choice question in one forward pass, but their answer depends on the order in which options are listed, and their probabilities carry a prior over answer labels. An invariant ordering operator is any fixed function that returns the same ordered option list for every input order of a fixed option set. Starting from any such order and averaging a listwise readout over its K cyclic shifts removes the input order, but the decision still depends on the chosen cyclic class: those $K$ shifts are only one of the (K-1)! classes, and different invariant operators can select different classes. We propose IJev, which repeatedly reorders the options by the cyclic-averaged, label-prior-corrected distribution and runs another cyclic average. Every iterate is exactly input-order-invariant. When the iteration does not converge, we average the round distributions rather than return the last round. On five benchmarks and five models, IJev has flip rate zero in every cell. The default uniform average over T=20 rounds substantially improves calibration over a single cyclic average, and its accuracy is comparable. A descriptive choice of horizon and averaging rule is best or tied-best for accuracy in all 25 settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01015 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:09:53.323Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).